Contextual Image Cropping and Report Generation

4. The method of claim 3, further comprising generating an error notification in response to determining that the anatomical feature is not included in the annotated portion of the diagnostic image.

5. The method of claim 4, wherein the error notification indicates that the annotated portion of the diagnostic image does not include an image of the anatomical feature.

6. The method of claim 3, wherein the natural language input is received based at least in part on audio detected by a microphone of the input device, and wherein the natural language input comprises dictated information comprising the report information and the report generation instructions.

7. The method of claim 3, wherein identifying, using the computer vision algorithm, the annotated portion of the diagnostic image is based on the natural language input.

9. The method of claim 3, wherein identifying the annotated portion of the diagnostic image comprises determining a cropping window that does not cross a gradient within-the diagnostic image and cropping the diagnostic image using the cropping window.

10. The method of claim 3, wherein identifying the annotated portion of the diagnostic image comprises selecting the computer vision algorithm from a set of computer vision algorithms based at least in part on the annotation.

12. The method of claim 3, wherein identifying the annotated portion of the diagnostic image comprises determining a cropping window surrounding an object associated with the annotation and identified by the computer vision algorithm, the cropping window shaped and positioned such that a perimeter of the cropping window does not cross a gradient within the diagnostic image.

13. The method of claim 3, wherein generating the medical report is based at least in part on the report generation instructions comprising inserting the annotated portion of the diagnostic image, and wherein the annotated portion of the diagnostic image is inserted into the medical report in response to receipt of the natural language input.

16. The system of claim 15, wherein the mobile device comprises an interface for interacting with and controlling at least one operation of the computing device from the mobile device.

17. The system of claim 14, wherein identifying the image of the computer-selected anatomical feature comprises determining a cropping window that does not cross a gradient within the diagnostic image and the diagnostic image is cropped to identify the image of the computer-selected anatomical feature.

19. The system of claim 14, wherein the medical report is stored as a JavaScript Object Notation (JSON) file.